@article{valley2exploringmultimodalmodelswith,
  title = {Valley2: Exploring Multimodal Models with Scalable Vision-Language Design},
  author = {Ziheng Wu and Zhenghao Chen and Ruipu Luo and Can Zhang and Yuan Gao and Zhentao He and Xian Wang and Haoran Lin and Minghui Qiu},
  year = {2025},
  eprint = {2501.05901},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2501.05901v2},
}